No-Regret Learning and Mixed Nash Equilibria: They Do Not Mix

Authors: Emmanouil-Vasileios Vlatakis-Gkaragkounis, Lampros Flokas, Thanasis Lianeas, Panayotis Mertikopoulos, Georgios Piliouras

NeurIPS 2020 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Theoretical Understanding the behavior of no-regret dynamics in general 𝑁-player games is a fundamental question in online learning and game theory. A folk result in the field states that, in finite games, the empirical frequency of play under no-regret learning converges to the game s set of coarse correlated equilibria. By contrast, our understanding of how the day-to-day behavior of the dynamics correlates to the game s Nash equilibria is much more limited, and only partial results are known for certain classes of games (such as zero-sum or congestion games). In this paper, we study the dynamics of follow the regularized leader (FTRL), arguably the most well-studied class of no-regret dynamics, and we establish a sweeping negative result showing that the notion of mixed Nash equilibrium is antithetical to no-regret learning. Specifically, we show that any Nash equilibrium which is not strict (in that every player has a unique best response) cannot be stable and attracting under the dynamics of FTRL. This result has significant implications for predicting the outcome of a learning process as it shows unequivocally that only strict (and hence, pure) Nash equilibria can emerge as stable limit points thereof.
Researcher Affiliation Collaboration Lampros Flokas Department of Computer Science Columbia University New York, NY 10025 lamflokas@cs.columbia.edu Emmanouil V. Vlatakis-Gkaragkounis Department of Computer Science Columbia University New York, NY 10025 emvlatakis@cs.columbia.edu Thanasis Lianeas School of Electrical and Computer Engineering National Technical University of Athens Athens,Greece lianeas@corelab.ntua.gr Panayotis Mertikopoulos Univ. Grenoble Alpes, CNRS, Inria, LIG & Criteo AI Lab panayotis.mertikopoulos@imag.fr Georgios Piliouras Engineering Systems and Design Singapore University of Technology and Design Singapore georgios@sutd.edu.sg
Pseudocode No The paper is theoretical and does not contain any pseudocode or algorithm blocks.
Open Source Code No The paper does not provide any concrete access to source code for the methodology described.
Open Datasets No The paper is a theoretical work focusing on mathematical analysis and proofs, not empirical evaluation with datasets. Therefore, it does not provide information about public datasets used for training.
Dataset Splits No The paper is a theoretical work and does not involve empirical experiments with dataset splits for training, validation, or testing.
Hardware Specification No The paper is theoretical and does not describe any experimental setup or mention hardware specifications.
Software Dependencies No The paper is theoretical and does not describe any experimental setup or list software dependencies with version numbers.
Experiment Setup No The paper is theoretical and does not include details about an experimental setup, hyperparameters, or training configurations.